[图书][B] Active preference-based learning of reward functions

D Sadigh, A Dragan, S Sastry, S Seshia - 2017 - escholarship.org
Our goal is to efficiently learn reward functions encoding a human's preferences for how a
dynamical system should act. There are two challenges with this. First, in many problems it is …
被引用次数：371 相关文章
[PDF] berkeley.edu

[PDF][PDF] Active Preference-Based Learning of Reward Functions

D Sadigh, AD Dragan, S Sastry, SA Seshia - people.eecs.berkeley.edu
Our goal is to efficiently learn reward functions encoding a human's preferences for how a
dynamical system should act. There are two challenges with this. First, in many problems it is …
[PDF] stanford.edu

[PDF][PDF] Active Preference-Based Learning of Reward Functions

D Sadigh, AD Dragan, S Sastry, SA Seshia - iliad.stanford.edu
Our goal is to efficiently learn reward functions encoding a human's preferences for how a
dynamical system should act. There are two challenges with this. First, in many problems it is …
[PDF] utexas.edu

[PDF][PDF] Active Preference-Based Learning of Reward Functions

D Sadigh, AD Dragan, S Sastry, SA Seshia - cs.utexas.edu
Our goal is to efficiently learn reward functions encoding a human's preferences for how a
dynamical system should act. There are two challenges with this. First, in many problems it is …
[PDF] roboticsproceedings.org

[PDF][PDF] Active Preference-Based Learning of Reward Functions

D Sadigh, AD Dragan, S Sastry, SA Seshia - m.roboticsproceedings.org
Our goal is to efficiently learn reward functions encoding a human's preferences for how a
dynamical system should act. There are two challenges with this. First, in many problems it is …
[PDF] archive.org

[PDF][PDF] Active Preference-Based Learning of Reward Functions

D Sadigh, AD Dragan, S Sastry, SA Seshia - scholar.archive.org
Our goal is to efficiently learn reward functions encoding a human's preferences for how a
dynamical system should act. There are two challenges with this. First, in many problems it is …
[PDF] roboticsproceedings.org

[PDF][PDF] Active Preference-Based Learning of Reward Functions

D Sadigh, AD Dragan, S Sastry, SA Seshia - roboticsproceedings.org
Our goal is to efficiently learn reward functions encoding a human's preferences for how a
dynamical system should act. There are two challenges with this. First, in many problems it is …
[PDF] roboticsproceedings.org

[PDF][PDF] Active Preference-Based Learning of Reward Functions

D Sadigh, AD Dragan, S Sastry, SA Seshia - roboticsproceedings.org
Our goal is to efficiently learn reward functions encoding a human's preferences for how a
dynamical system should act. There are two challenges with this. First, in many problems it is …
[PDF] berkeley.edu

[PDF][PDF] Active Preference-Based Learning of Reward Functions

D Sadigh, AD Dragan, S Sastry, SA Seshia - people.eecs.berkeley.edu
Our goal is to efficiently learn reward functions encoding a human's preferences for how a
dynamical system should act. There are two challenges with this. First, in many problems it is …